Speech Command Recognition in Computationally Constrained Environments
with a Quadratic Self-organized Operational Layer
- URL: http://arxiv.org/abs/2011.11436v2
- Date: Wed, 10 Feb 2021 18:28:13 GMT
- Title: Speech Command Recognition in Computationally Constrained Environments
with a Quadratic Self-organized Operational Layer
- Authors: Mohammad Soltanian and Junaid Malik and Jenni Raitoharju and
Alexandros Iosifidis and Serkan Kiranyaz and Moncef Gabbouj
- Abstract summary: We propose a network layer to enhance the speech command recognition capability of a lightweight network.
The employed method borrows the ideas of Taylor expansion and quadratic forms to construct a better representation of features in both input and hidden layers.
This richer representation results in recognition accuracy improvement as shown by extensive experiments on Google speech commands (GSC) and synthetic speech commands (SSC) datasets.
- Score: 92.37382674655942
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Automatic classification of speech commands has revolutionized human computer
interactions in robotic applications. However, employed recognition models
usually follow the methodology of deep learning with complicated networks which
are memory and energy hungry. So, there is a need to either squeeze these
complicated models or use more efficient light-weight models in order to be
able to implement the resulting classifiers on embedded devices. In this paper,
we pick the second approach and propose a network layer to enhance the speech
command recognition capability of a lightweight network and demonstrate the
result via experiments. The employed method borrows the ideas of Taylor
expansion and quadratic forms to construct a better representation of features
in both input and hidden layers. This richer representation results in
recognition accuracy improvement as shown by extensive experiments on Google
speech commands (GSC) and synthetic speech commands (SSC) datasets.
Related papers
- The OCON model: an old but green solution for distributable supervised classification for acoustic monitoring in smart cities [0.28675177318965045]
This paper focuses on vowel phonemes classification and speakers recognition for the Automatic Speech Recognition domain.
For our case-study, the ASR model runs on a proprietary sensing and lightning system, exploited to monitor acoustic and air pollution on urban streets.
We formalize combinations of pseudo-Neural Architecture Search and Hyper-s Tuning experiments, using an informed grid-search methodology, to achieve classification accuracy comparable to nowadays most complex architectures.
arXiv Detail & Related papers (2024-10-05T09:47:54Z) - Improved Contextual Recognition In Automatic Speech Recognition Systems
By Semantic Lattice Rescoring [4.819085609772069]
We propose a novel approach for enhancing contextual recognition within ASR systems via semantic lattice processing.
Our solution consists of using Hidden Markov Models and Gaussian Mixture Models (HMM-GMM) along with Deep Neural Networks (DNN) models for better accuracy.
We demonstrate the effectiveness of our proposed framework on the LibriSpeech dataset with empirical analyses.
arXiv Detail & Related papers (2023-10-14T23:16:05Z) - Representation Learning With Hidden Unit Clustering For Low Resource
Speech Applications [37.89857769906568]
We describe an approach to self-supervised representation learning from raw audio using a hidden unit clustering (HUC) framework.
The input to the model consists of audio samples that are windowed and processed with 1-D convolutional layers.
The HUC framework, allowing the categorization of the representations into a small number of phoneme-like units, is used to train the model for learning semantically rich speech representations.
arXiv Detail & Related papers (2023-07-14T13:02:10Z) - HCAM -- Hierarchical Cross Attention Model for Multi-modal Emotion
Recognition [41.837538440839815]
We propose a hierarchical cross-attention model (HCAM) approach to multi-modal emotion recognition.
The input to the model consists of two modalities, i) audio data, processed through a learnable wav2vec approach and, ii) text data represented using a bidirectional encoder representations from transformers (BERT) model.
In order to incorporate contextual knowledge and the information across the two modalities, the audio and text embeddings are combined using a co-attention layer.
arXiv Detail & Related papers (2023-04-14T03:25:00Z) - Surrogate Gradient Spiking Neural Networks as Encoders for Large
Vocabulary Continuous Speech Recognition [91.39701446828144]
We show that spiking neural networks can be trained like standard recurrent neural networks using the surrogate gradient method.
They have shown promising results on speech command recognition tasks.
In contrast to their recurrent non-spiking counterparts, they show robustness to exploding gradient problems without the need to use gates.
arXiv Detail & Related papers (2022-12-01T12:36:26Z) - Multimodal Emotion Recognition using Transfer Learning from Speaker
Recognition and BERT-based models [53.31917090073727]
We propose a neural network-based emotion recognition framework that uses a late fusion of transfer-learned and fine-tuned models from speech and text modalities.
We evaluate the effectiveness of our proposed multimodal approach on the interactive emotional dyadic motion capture dataset.
arXiv Detail & Related papers (2022-02-16T00:23:42Z) - Improved Speech Emotion Recognition using Transfer Learning and
Spectrogram Augmentation [56.264157127549446]
Speech emotion recognition (SER) is a challenging task that plays a crucial role in natural human-computer interaction.
One of the main challenges in SER is data scarcity.
We propose a transfer learning strategy combined with spectrogram augmentation.
arXiv Detail & Related papers (2021-08-05T10:39:39Z) - SAR-NAS: Skeleton-based Action Recognition via Neural Architecture
Searching [18.860051578038608]
We encode a skeleton-based action instance into a tensor and define a set of operations to build two types of network cells: normal cells and reduction cells.
Experiments on the challenging NTU RGB+D and Kinectics datasets have verified that most of the networks developed to date for skeleton-based action recognition are likely not compact and efficient.
The proposed method provides an approach to search for such a compact network that is able to achieve comparative or even better performance than the state-of-the-art methods.
arXiv Detail & Related papers (2020-10-29T03:24:15Z) - Reservoir Memory Machines as Neural Computers [70.5993855765376]
Differentiable neural computers extend artificial neural networks with an explicit memory without interference.
We achieve some of the computational capabilities of differentiable neural computers with a model that can be trained very efficiently.
arXiv Detail & Related papers (2020-09-14T12:01:30Z) - AutoSpeech: Neural Architecture Search for Speaker Recognition [108.69505815793028]
We propose the first neural architecture search approach approach for the speaker recognition tasks, named as AutoSpeech.
Our algorithm first identifies the optimal operation combination in a neural cell and then derives a CNN model by stacking the neural cell for multiple times.
Results demonstrate that the derived CNN architectures significantly outperform current speaker recognition systems based on VGG-M, ResNet-18, and ResNet-34 back-bones, while enjoying lower model complexity.
arXiv Detail & Related papers (2020-05-07T02:53:47Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.